Dataset Versions

v1

2024-08-28 12:37pm

Generated on Aug 28, 2024

Dataset Split

Train Set 95%
5580Images
Valid Set 4%
220Images
Test Set 2%
104Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Tile: 2 rows x 2 columns
Modify Classes: 1 remapped, 0 dropped

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Noise: Up to 0.1% of pixels